Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2663 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.7353. Min Act: -0.1700
Data Index: 3031233 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.7193. Min Act: -0.1700
Data Index: 2979649 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6873. Min Act: -0.1700
Data Index: 2322776 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.7033. Min Act: -0.1700
Data Index: 6523424 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.7033. Min Act: -0.1700
Data Index: 7455297 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6873. Min Act: -0.1700
Data Index: 6279177 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6713. Min Act: -0.1700
Data Index: 5674205 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6392. Min Act: -0.1700
Data Index: 2657880 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6392. Min Act: -0.1700
Data Index: 6734589 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6392. Min Act: -0.1700
Data Index: 6334550 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6392. Min Act: -0.1700
Data Index: 4564624 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6392. Min Act: -0.1700
Data Index: 7896929 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6392. Min Act: -0.1700
Data Index: 3276649 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6070. Min Act: -0.1700
Data Index: 8397895 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6231. Min Act: -0.1700
Data Index: 7239172 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6231. Min Act: -0.1700
Data Index: 8583252 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6231. Min Act: -0.1700
Data Index: 8755094 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6231. Min Act: -0.1700
Data Index: 6952169 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6231. Min Act: -0.1700
Data Index: 49149 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7353. Min Range: -2.7353
Max Act: 2.6231. Min Act: -0.1700
Data Index: 5568208 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19